Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -learning
    -0.07
    	Version
    -0.07
     telev
    -0.06
    orption
    -0.06
     listItem
    -0.06
    šel
    -0.06
    _concat
    -0.06
    thin
    -0.06
     FD
    -0.06
    _READONLY
    -0.06
    POSITIVE LOGITS
    stants
    0.07
    ляется
    0.07
     cheats
    0.07
    _security
    0.07
     discovered
    0.06
    :a
    0.06
    Manufacturer
    0.06
    戲
    0.06
    """↵↵
    0.06
    มหานคร
    0.06
    Act Density 0.002%

    No Known Activations